UnifyBench

RankingEffort benchmarks

MiniMax-M1-40k · Reasoning

Compare models

9 measured results · 1 effort settings · 9 benchmark/harness combinations

Model evidence and sources →

Change model

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare with

Capability profile

One configuration, seven capabilities

Comparison score · 0–100
MiniMax-M1-40k · Reasoning capability radarComparison scores from 0 to 100. Unknown capabilities have no point; lines stop at gaps. Hollow points are preliminary. Exact values and support labels follow the chart.AgenticHard reasoningCodingHuman prefKnowledgeMultimodalLong context50100MiniMax-M1-40k · Reasoning · Agentic: 3.0 · PreliminaryMiniMax-M1-40k · Reasoning · Hard reasoning: 3.7 · SupportedMiniMax-M1-40k · Reasoning · Coding: 3.1 · SupportedMiniMax-M1-40k · Reasoning · Knowledge: 5.6 · Supported

Gaps are unknown, not zero. Hollow points are preliminary.

  • Agentic

    A3.0Preliminary

  • Hard reasoning

    A3.7Supported

  • Coding

    A3.1Supported

  • Human pref

    Unknown

  • Knowledge

    A5.6Supported

  • Multimodal

    Unknown

  • Long context

    Unknown

Each profile belongs to the named configuration. Capability scores use a shared panel for all axes, distinct from the overall ranking panel; they are not accuracy percentages or direct head-to-head wins.

Capability score evidence

MiniMax-M1-40k · Reasoning: 1.1 overall comparison score. Meets the overall evidence requirements.

4 areas measured. The available task mix affects this estimate; missing areas remain unknown.

Which sources carry the weight?
  • Artificial Analysis · 100.0% direct comparison weight · independent of the model provider
Which benchmark families carry the weight?
  • MMLU-Pro · 11.7% direct comparison weight
  • IFBench · 11.7% direct comparison weight
  • LiveCodeBench · 11.6% direct comparison weight
  • Aime · 11.6% direct comparison weight
  • math500 · 11.5% direct comparison weight
  • Other families (4) · 41.9% direct comparison weight

These shares describe direct comparison weight, not fractions of the final score or confidence. Source balancing does not give every family equal weight or remove correlations between overlapping sources.

How sensitive is this score?

The audit removes one source at a time and refits against the same overall reference panel. These published results use the matching dataset audited 2026-10-20.

Both ranks use the same surviving configurations for each removal. The cohort starts with 444 configurations supported in the original audit, including separate effort settings. These are diagnostic positions, not the default leaderboard ranks. Eligibility is not rechecked after removal.

What changes when a source is removed?
Removed sourceRank before → afterRank movementCohort remaining / lost supportScore after (change)
Artificial AnalysisComparison support lost; no rank203 remaining / 241 lostUnavailable
ARC Prize351 → 350Up 1444 remaining / 0 lost1.4 (+0.4 points)
Datacurve351 → 351No movement444 remaining / 0 lost0.8 (-0.2 points)
LiveCodeBench351 → 351No movement444 remaining / 0 lost1.1 (-0.0 points)
Scale351 → 351No movement444 remaining / 0 lost1.3 (+0.2 points)
Terminal-Bench351 → 351No movement444 remaining / 0 lost1.1 (-0.0 points)
Cognition351 → 351No movement444 remaining / 0 lost1.0 (-0.0 points)
LiveBench350 → 350No movement443 remaining / 1 lost1.1 (+0.0 points)
SWE-rebench351 → 350Up 1444 remaining / 0 lost1.1 (+0.0 points)
Epoch AI338 → 336Up 2431 remaining / 13 lost1.1 (+0.0 points)
Vals AI350 → 350No movement443 remaining / 1 lost1.0 (-0.0 points)
Provider reports · Anthropic351 → 351No movement444 remaining / 0 lost1.1 (-0.0 points)
Provider reports · Moonshot AI351 → 351No movement444 remaining / 0 lost1.0 (-0.0 points)
Provider reports · Meta351 → 351No movement444 remaining / 0 lost1.1 (-0.0 points)
Provider reports · Mistral351 → 351No movement444 remaining / 0 lost1.1 (+0.0 points)
Provider reports · OpenAI351 → 351No movement444 remaining / 0 lost1.1 (+0.0 points)
All provider reports351 → 351No movement444 remaining / 0 lost1.0 (-0.0 points)

Lost support means a configuration no longer has a comparison path to the complete reference panel. Its rank is unavailable. A surviving path alone does not establish leaderboard eligibility.

Overlapping sources may remain correlated even with source balancing. Leave-one-source-out movement is a sensitivity diagnostic, not a spread of source-specific ranks or a confidence measure. Scoring methodology · Dated configuration audit

Every benchmark family
Removed evidenceRecomputed scoreChange
aime1.4+0.4
arc-agi1.4+0.3
deepswe0.8-0.2
terminal-bench1.2+0.2
omniscience0.9-0.1
math5001.0-0.1
mmmu-pro1.2+0.1
livecodebench1.0-0.1
epoch-game-puzzles1.0-0.1
hle1.1+0.1
mmlu-pro1.0-0.1
simpleqa1.1+0.1
ifbench1.0-0.1
critpt1.0-0.1
gpqa1.0-0.0
swe-rebench1.1+0.0
frontiercode1.0-0.0
livebench-instructions1.1+0.0
gdp-pdf1.1+0.0
multi-swe-bench1.0-0.0
tau-bench1.0-0.0
arc-agi-31.1-0.0
livebench-language1.1+0.0
apex-agents1.1+0.0
terminal-bench-science1.1+0.0
aa-lcr1.1-0.0
enigma-eval1.1-0.0
livebench-coding1.1-0.0
gmmlu1.1+0.0
swe-atlas-qna1.1-0.0
harvey1.1-0.0
analyst-agent1.1+0.0
itbench1.1-0.0
livebench-reasoning1.1-0.0
vibe-code1.1-0.0
briefcase1.1-0.0
automationbench1.1-0.0
swe-atlas-test-writing1.1-0.0
vals-code-migration1.1-0.0
vals-finance-agent1.1-0.0
vals-legal-research1.1-0.0
gdpval1.1+0.0
vals-tax-agent1.1-0.0
vals-excel-modeling1.1-0.0
frontiermath1.1+0.0
livebench-math1.1+0.0
enterprise-ops1.1+0.0
swe-atlas-refactoring1.1-0.0
swe-bench-pro1.1+0.0
livebench-data1.1-0.0
What evidence is missing from the fit?

Across all collected settings for this model: 9 observations, 9 contributing, 0 matched without graph weight and 0 excluded. Counts do not establish rank eligibility.

    Inspect every observation and exclusion →

    Benchmark results

    These are published benchmark scores. Supported effort estimates also appear on the Capability leaderboard. Results from different harnesses occupy different rows. Missing cells stay unknown; no scores are copied between effort levels.

    Benchmark / sourceReasoning
    AIME 2025Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings
    Benchmark details

    Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

    Unit: percent. Source collected 2026-10-18.

    13.67%
    Reported settings

    MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified

    GPQA DiamondArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings
    Benchmark details

    Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

    Unit: percent. Source collected 2026-10-18.

    68.18%
    Reported settings

    MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified

    Humanity's Last ExamArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings
    Benchmark details

    Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

    Unit: percent. Source collected 2026-10-18.

    7.83%
    Reported settings

    MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified

    IFBenchArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings
    Benchmark details

    Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

    Unit: percent. Source collected 2026-10-18.

    41.22%
    Reported settings

    MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified

    LiveCodeBenchArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings
    Benchmark details

    Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

    Unit: percent. Source collected 2026-10-18.

    65.71%
    Reported settings

    MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified

    MATH-500Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings
    Benchmark details

    Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

    Unit: percent. Source collected 2026-10-18.

    97.2%
    Reported settings

    MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified

    MMLU-ProArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings
    Benchmark details

    Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

    Unit: percent. Source collected 2026-10-18.

    80.83%
    Reported settings

    MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified

    𝜏²-Bench TelecomArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings
    Benchmark details

    Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

    Unit: percent. Source collected 2026-10-18.

    31.58%
    Reported settings

    MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified

    Terminal-Bench HardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings
    Benchmark details

    Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

    Unit: percent. Source collected 2026-10-18.

    2.27%
    Reported settings

    MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified

    What these comparisons mean

    Each source reports its own effort labels. Matching labels do not establish equal compute budgets or identical fallback behavior. Open Reported settings to inspect the exact model name, agent and task coverage. Multiple results at one level remain visible rather than selecting the best. Source-reported None or Non-reasoning labels are not treated as evidence that an API supports those settings.

    These measurements use their own dated source collection. The leaderboard fits identified configurations jointly; it contains no pooled model ratings. Explicit thinking budgets are separate configurations. Read the methodology.

    Download all effort benchmark results · 8,915 results across 259 models · Collected 2026-10-18